backkon

高博，请问13讲中338页说 深度值乘以0.4的结果——也就是纯白点（数值为1.0）的深度约2.5米 灰度图的像素值范围不是[0，255]吗？为什么像素值1代表白点，不应该是255代表白点吗？我看前面也没有进行过归一化处理呀

loss unchanged after about 200 epochs

1

Hello, I trained PFLD according to your code. The loss on the validation dataset is unchanged after about 200 epochs, and finally nme is 0.074. Why is this? Looking forward...

Why L is set to 2 for calculating SSIM

1

Hello, your work is excellent! But I have some questions, I would like to ask why L is set to 2 in the Matlab code for calculating SSIM, and should...

about lesson8:DCGAN

5

Why do I get the log as shown below: ``` [0/20][0/32] Loss_D: 1.8010 Loss_G: 8.0963 D(x): 0.4317 D(G(z)): 0.3617 / 0.0005 [0/20][10/32] Loss_D: 7.5290 Loss_G: 38.1183 D(x): 0.9269 D(G(z)): 0.9958...

batched

2

is the utils.py file right? your source code is as follows: method = 'cluster_weighted_diounms' #method = 'merge' batched = 'batch' in method # run once per image, all classes simultaneously...

A question about dataloader

2

I want to know why I debug this line: for batch, (lr, hr, _,) in enumerate(self.loader_train): ... It will go back to the main.py and rerun the global code?